Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4419 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7329. Min Range: -6.7329
Max Act: 6.7329. Min Act: -0.1700
Data Index: 6932886 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7329. Min Range: -6.7329
Max Act: 6.6704. Min Act: -0.1700
Data Index: 847822 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7329. Min Range: -6.7329
Max Act: 6.6391. Min Act: -0.1700
Data Index: 2880653 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7329. Min Range: -6.7329
Max Act: 6.5454. Min Act: -0.1700
Data Index: 3744822 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7329. Min Range: -6.7329
Max Act: 6.5141. Min Act: -0.1700
Data Index: 4073325 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7329. Min Range: -6.7329
Max Act: 6.5141. Min Act: -0.1700
Data Index: 907003 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7329. Min Range: -6.7329
Max Act: 6.4829. Min Act: -0.1700
Data Index: 843914 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7329. Min Range: -6.7329
Max Act: 6.4204. Min Act: -0.1700
Data Index: 948455 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7329. Min Range: -6.7329
Max Act: 6.3579. Min Act: -0.1700
Data Index: 691636 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7329. Min Range: -6.7329
Max Act: 6.3266. Min Act: -0.1700
Data Index: 1212999 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7329. Min Range: -6.7329
Max Act: 6.3266. Min Act: -0.1700
Data Index: 4291192 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7329. Min Range: -6.7329
Max Act: 6.3266. Min Act: -0.1700
Data Index: 392429 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7329. Min Range: -6.7329
Max Act: 6.2954. Min Act: -0.1700
Data Index: 2550839 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7329. Min Range: -6.7329
Max Act: 6.2954. Min Act: -0.1700
Data Index: 6595950 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7329. Min Range: -6.7329
Max Act: 6.2954. Min Act: -0.1700
Data Index: 572440 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7329. Min Range: -6.7329
Max Act: 6.2954. Min Act: -0.1700
Data Index: 117813 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7329. Min Range: -6.7329
Max Act: 6.3266. Min Act: -0.1700
Data Index: 1438272 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7329. Min Range: -6.7329
Max Act: 6.2954. Min Act: -0.1700
Data Index: 6552713 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7329. Min Range: -6.7329
Max Act: 6.2641. Min Act: -0.1700
Data Index: 5414418 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7329. Min Range: -6.7329
Max Act: 6.2641. Min Act: -0.1700
Data Index: 114730 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #19